Table 2 Parameters used to train MNIST and CIFAR10 networks
Parameter | MNIST model | CIFAR model |
|---|---|---|
Learning rate | 0.1 | 0.01 |
Momentum | 0.9 | 0.9 |
Dropout | 0.5 | (see Table 1) |
Batch size | 128 | 100 |
Epochs | 50 | 75 |
Parameter | MNIST model | CIFAR model |
|---|---|---|
Learning rate | 0.1 | 0.01 |
Momentum | 0.9 | 0.9 |
Dropout | 0.5 | (see Table 1) |
Batch size | 128 | 100 |
Epochs | 50 | 75 |